diff --git a/models.yaml b/models.yaml index 6ab24f1..25a3cd5 100644 --- a/models.yaml +++ b/models.yaml @@ -746,8 +746,8 @@ - name: gemma-4-26b-a4b-it type: chat max_input_tokens: 262144 - input_price: 0.07 - output_price: 0.34 + input_price: 0.042 + output_price: 0.22 max_output_tokens: 32768 supports_vision: true supports_function_calling: true @@ -2015,6 +2015,14 @@ - low - medium - high + - name: xai/grok-4.6 + type: chat + max_input_tokens: 524288 + input_price: 2.0 + output_price: 6.0 + max_output_tokens: 500000 + supports_vision: true + supports_function_calling: true - name: claude-opus-5@default type: chat max_input_tokens: 1000000 @@ -2161,6 +2169,14 @@ - medium - high default_reasoning_effort: minimal + - name: xai/grok-4.3 + type: chat + max_input_tokens: 200000 + input_price: 1.25 + output_price: 2.5 + max_output_tokens: 30000 + supports_vision: true + supports_function_calling: true - name: claude-opus-4-7@default type: chat max_input_tokens: 1000000 @@ -2176,6 +2192,22 @@ - high - xhigh - max + - name: xai/grok-4.20-non-reasoning + type: chat + max_input_tokens: 2000000 + input_price: 1.25 + output_price: 2.5 + max_output_tokens: 30000 + supports_vision: true + supports_function_calling: true + - name: xai/grok-4.20-reasoning + type: chat + max_input_tokens: 2000000 + input_price: 1.25 + output_price: 2.5 + max_output_tokens: 30000 + supports_vision: true + supports_function_calling: true - name: gemini-3.1-flash-lite-preview type: chat max_input_tokens: 1048576 @@ -2277,6 +2309,22 @@ - medium - high default_reasoning_effort: high + - name: xai/grok-4.1-fast-non-reasoning + type: chat + max_input_tokens: 128000 + input_price: 0.2 + output_price: 0.5 + max_output_tokens: 30000 + supports_vision: true + supports_function_calling: true + - name: xai/grok-4.1-fast-reasoning + type: chat + max_input_tokens: 128000 + input_price: 0.2 + output_price: 0.5 + max_output_tokens: 30000 + supports_vision: true + supports_function_calling: true - name: moonshotai/kimi-k2-thinking-maas type: chat max_input_tokens: 262144 @@ -5261,11 +5309,35 @@ supports_function_calling: true - provider: deepseek models: + - name: deepseek-flash + type: chat + max_input_tokens: 1000000 + input_price: 0.15 + output_price: 0.6 + max_output_tokens: 384000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - high + - max + - name: deepseek-v4-flash + type: chat + max_input_tokens: 1000000 + input_price: 0.15 + output_price: 0.6 + max_output_tokens: 384000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - low + - high + - max - name: deepseek-v4-flash-vision-exp type: chat max_input_tokens: 1000000 - input_price: 0.14 - output_price: 0.28 + input_price: 0.15 + output_price: 0.6 max_output_tokens: 384000 supports_vision: true supports_function_calling: true @@ -5283,17 +5355,6 @@ reasoning_levels: - high - max - - name: deepseek-v4-flash - type: chat - max_input_tokens: 1000000 - input_price: 0.14 - output_price: 0.28 - max_output_tokens: 384000 - supports_function_calling: true - reasoning_levels: - - low - - high - - max - name: deepseek-chat type: chat max_input_tokens: 64000 @@ -6583,9 +6644,9 @@ - name: google/gemma-4-26b-a4b-it type: chat max_input_tokens: 262144 - input_price: 0.07 - output_price: 0.34 - max_output_tokens: 16384 + input_price: 0.042 + output_price: 0.22 + max_output_tokens: 32768 supports_vision: true supports_function_calling: true - name: google/gemma-4-26b-a4b-it:free @@ -6695,6 +6756,14 @@ output_price: 0.0 max_output_tokens: 32768 supports_function_calling: true + - name: inclusionai/ling-3.0-flash-vl:free + type: chat + max_input_tokens: 262144 + input_price: 0.0 + output_price: 0.0 + max_output_tokens: 32768 + supports_vision: true + supports_function_calling: true - name: kwaipilot/kat-coder-pro-v2 type: chat max_input_tokens: 262144 @@ -6732,9 +6801,9 @@ - name: meta-llama/llama-3.1-70b-instruct type: chat max_input_tokens: 131072 - input_price: 0.4 - output_price: 0.4 - max_output_tokens: 16384 + input_price: 0.72 + output_price: 0.72 + max_output_tokens: 8192 supports_function_calling: true - name: meta-llama/llama-3.1-8b-instruct type: chat @@ -7153,8 +7222,8 @@ - name: moonshotai/kimi-k3 type: chat max_input_tokens: 1048576 - input_price: 3.0 - output_price: 15.0 + input_price: 2.6 + output_price: 13.0 max_output_tokens: 943718 supports_vision: true supports_function_calling: true @@ -8342,9 +8411,9 @@ - name: qwen/qwen3-30b-a3b-instruct-2507 type: chat max_input_tokens: 262144 - input_price: 0.0482 - output_price: 0.1931 - max_output_tokens: 32000 + input_price: 0.09 + output_price: 0.3 + max_output_tokens: 235929 supports_function_calling: true - name: qwen/qwen3-30b-a3b-thinking-2507 type: chat @@ -8863,8 +8932,8 @@ - name: upstage/solar-pro4 type: chat max_input_tokens: 524288 - input_price: 0.03 - output_price: 0.12 + input_price: 0.09 + output_price: 0.36 max_output_tokens: 131072 supports_function_calling: true - name: writer/palmyra-x5 @@ -8989,7 +9058,7 @@ supports_function_calling: true - name: z-ai/glm-4.7-flash type: chat - max_input_tokens: 202752 + max_input_tokens: 200000 input_price: 0.0605 output_price: 0.4 max_output_tokens: 117964 @@ -9165,9 +9234,9 @@ - name: ~z-ai/glm-latest type: chat max_input_tokens: 1310720 - input_price: 1.0075 - output_price: 3.41 - max_output_tokens: 235929 + input_price: 0.7 + output_price: 2.2 + max_output_tokens: 128000 supports_function_calling: true - provider: github models: @@ -9272,6 +9341,20 @@ max_input_tokens: 131072 - provider: deepinfra models: + - name: deepseek-ai/DeepSeek-V4.1-Flash + type: chat + max_input_tokens: 1048576 + input_price: 0.3 + output_price: 1.2 + max_output_tokens: 384000 + supports_vision: true + supports_function_calling: true + reasoning_levels: + - none + - low + - high + - xhigh + - max - name: zai-org/GLM-5.3-Flash type: chat max_input_tokens: 1048576